|Publication number||US7525913 B2|
|Application number||US 10/195,492|
|Publication date||Apr 28, 2009|
|Filing date||Jul 16, 2002|
|Priority date||Dec 19, 2001|
|Also published as||CA2365688A1, EP1322079A2, EP1322079A3, EP1322079B1, US20030112757|
|Publication number||10195492, 195492, US 7525913 B2, US 7525913B2, US-B2-7525913, US7525913 B2, US7525913B2|
|Inventors||Mark Jason Thibodeau, John William Galway, Jason Sterne, Michael Wayne Mitchell, Peter Donovan|
|Original Assignee||Alcatel-Lucent Canada Inc.|
|Export Citation||BiBTeX, EndNote, RefMan|
|Patent Citations (17), Referenced by (1), Classifications (16), Legal Events (6)|
|External Links: USPTO, USPTO Assignment, Espacenet|
The invention relates to a system and method providing traffic management of cells being processed by a network element.
In a communication switch, a switch fabric is provided. The switch fabric may be implemented as a conventional cell space switch whereby cells are received at any of N input ports and switched to any of N output ports through a connection. The design of such fabrics are rather simple, and typically include buffering at each output port. Buffering within the fabric may not be adequate, depending on demands from periphery subsystems, resulting in loss of data cells at the fabric.
Backpressure is a well-known feedback technique to reduce or prevent cell loss when the switch fabric experiences congestion. The fabric sends a Backpressure Indication (feedback message) for a congested output port to the peripheral subsystem, which in response holds back sending cells destined to that port. Typically all input ports which are connected to the output port receive the same backpressure signal. Accordingly it is desirable to minimize the need for backpressure signalling.
For example, in a typical N×N switching architecture, the use of backpressure would allow congestion in the switching fabric to “push-back” to the input port. When an input port receives a backpressure indication from an output port, the input port stops sending data transmissions to the output port. While Quality of Service (QoS) standards for transmission rates are ensured using backpressure signalling, the use of backpressure signalling is disruptive to the traffic flow for an input port.
There is a need for a system and method for regulating cell traffic to reduce the generation I/O of backpressure signals that improves upon prior art systems.
In a first aspect, a method of controlling timing of release of traffic provided to a communication switch is provided. The traffic originates from at least one source, is directed to a common ingress point of the switch and is directed to a common egress point in the switch. The egress point has a maximum egress transmission rate. The traffic comprises at least one datastream. The method comprises for each datastream, establishing a maximum cell release rate such that a sum of each maximum cell release rate does not exceed the maximum egress transmission rate, and for each datastream, utilizing the maximum cell release rate to govern release of local traffic the datastream from the ingress point.
The method may have the common ingress point as a queue in an ingress line card and the common egress point as an egress line card.
The method may have the release of local traffic further governed by a backpressure indication of traffic for the datastream.
The method may have the release of the traffic further governed by an indication of availability of local traffic for the datastream to be transmitted at the ingress point.
In a second aspect, a circuit for controlling timing of release of traffic for a communication switch is provided. The traffic originates from at least one source, is directed to a common ingress point of the switch and is directed to a common egress point in the switch. The egress point has a maximum egress transmission rate. The traffic comprises at least one datastream. The circuit comprises at the ingress point, for each datastream, a counter module adapted to generate a local traffic pulse signal to control release of local traffic of the datastream. The local traffic pulse signal provides a limited release rate for the local traffic of the datastream. The limited release rate is defined by the maximum egress transmission rate, such that a sum of all limited release rates for all datastreams does not exceed the maximum egress transmission rate.
The circuit may have for each datastream, a second counter module adapted to generate a local traffic release signal utilizing the local traffic pulse signal. The local traffic release signal is generated when traffic is available in the datastream.
The circuit may have the local traffic release signal generated when there is no backpressure in the datastream.
The circuit may further comprise a shaper associated with an output of said second counter module for traffic from each datastream.
In other aspects of the invention, various combinations and subset of the above aspects are provided.
The foregoing and other aspects of the invention will become more apparent from the following description of specific embodiments thereof and the accompanying drawings which illustrate, by way of example only, the principles of the invention. In the drawings, where like elements feature like reference numerals (and wherein individual elements bear unique alphabetical suffixes):
The description which follows, and the embodiments described therein, are provided by way of illustration of an example, or examples, of particular embodiments of the principles of the present invention. These examples are provided for the purposes of explanation, and not limitation, of those principles and of the invention. In the description, which follows, like parts are marked throughout the specification and the drawings with the same respective reference numerals.
Following is a description of a network element associated with the embodiment. Referring to
Switches 108 and 110 incorporate the traffic shaping system of the embodiment. It will be appreciated that terms such as “routing switch”, “communication switch”, “communication device”, “switch”, “network element” and other terms known in the art may be used to describe switch 108. Further, while the embodiment is described for switch 108, it will be appreciated that the system and method described herein may be adapted to any data switching system.
Egress line cards 204 provide outputs ports for I/O to switch 108. The output ports may connect to other CPEs 102 or they may connect to other network elements 108 in cloud 106, thereby providing an access point to CPEs 104.
It will be appreciated that for the particular configuration I/O of switch 108 shown, the ingress direction for traffic flow relative to core 200 is from CPEs 102 through line cards 202 to core 200 and the egress direction of traffic flow is from core 200 to line cards 204 to other elements 102 q or other switches 108. Dotted line 212 demarks the border of the ingress and egress sides of switch 108 with the ingress side of switch 108 on the left side and the egress side the right side of line 212.
In the embodiment, each input port on ingress line card 202 has a throughput capacity set according to OC-48 bandwidth standards and each output port on egress line card 204 has a throughput capacity set according to OC-3 bandwidth standards. It will be appreciated that other bandwidth capabilities may be provided on either the ingress or egress sides.
Other elements of switch 108 include communication links which enable switching shelves 200, line cards 202 and 204 and the control complex 206 to communicate data and status information with each other. High Speed Inter Shelf Links (HISL) 208 link control complex with switching fabric 200. HISLs 208 also link switching fabric shelves 200 with line cards 202 and 204. Terminal 210 is connected to switch 108 and runs controlling software, which allows an operator to modify, and control the operation of, switch 108.
Following is a description of backpressure issues associated with switch 108.
Accordingly, the embodiment provides a mechanism wherein each line card 202A and 202B can individually shape their traffic from their respective CPEs 102A . . . 102N and 102Q . . . 102X to minimize the production of backpressure signals. The shaping of the traffic is implemented by providing a guaranteed minimum inter-cell gap between cells transmitted by line card 202 into core 200. Traffic may be referred to as a datastream for a particular source.
CPE Bandwidth 102A 7 Mbps 102B 5 Mbps 102N 6 Mbps
For the example, line card 204 is receiving all the traffic from the CPEs and has a limit of 6 Mbps. Line card 202A determines that the total bandwidth requested by CPEs 102A . . . 102N exceeds bandwidth the capacity of line card 204. Accordingly, the embodiment limits the cumulative traffic from CPEs 102A . . . 102N to 5 Mbps. The line card 202A may apportion the bandwidth of the connected CPEs as follows:
CPE Restricted Bandwidth 102A 3 Mbps 102B 1 Mbps 102N 1 Mbps Total 5 Mbps
Accordingly, backpressure signalling would not be generated by line card 204.
Similarly, line card 202B has another independent system which regulates the bandwidth provided to each of its connected CPEs 102Q, 102R . . . 102X. The embodiment enables independent programming of bandwidth restrictions to individual line cards 202.
The embodiment also allows line cards 202A and 202B to absorb local backpressure traffic from each of its connected CPEs. However, if the local backpressure traffic persists for too long of a time, the embodiment would discard the traffic.
Further detail on each of the I/O card 302 and the line card 300 are provided below, using an example of a packet transmitted by CPE 102A. Initially, a packet is generated by CPE 102A and is transmitted along its optical link 306 to line card 302A. The packet is encoded in Packet Over SONET (POS) data. It will be appreciated that other encoding protocols may be used. The POS data is received at I/O card 302A at framer 308 which converts the serial POS data into parallel words of data. As the data is in packet form, it can be of variable length, which impacts the length of the parallel words of data. From framer 308, the parallel words of data, which collectively comprise a packet, are provided to error check module 310. An electrical signal encoding the parallel words of data is sent from error check module 310 across midplane 304 to line card 300.
At line card 300, the parallel words of data are received at I/O card 312. I/O card 312 provides automatic protection switching (APS). Accordingly, there would be a redundant set of I/O cards connected to line card 300. The I/O card selector would accept data from the operating I/O card. From I/O card 312, the data is provided to traffic processor 314 as a parallel stream of data.
Traffic processor 314 provides packet manipulation including header swapping on the data and policing of data transmission rate. In the embodiment, traffic processor 314 is a specialized communication processor from IBM, namely NP4GS3, known as IBM Power NP Network Processor, which utilizes a “Ranier” data format for encoding the packets, which is a proprietary IBM format. It will be appreciated that other processors and other formats may be used. The processor 314 converts the packet data into a number of cells, each being a 64 byte segment, having either 48 or 54 bytes of data therein with the remainder being header information. As mentioned earlier, a packet may comprise one or more cells. In the embodiment, the cells are the elemental data blocks which are sequentially transmitted with a minimum gap between cells. It will be appreciated that in other embodiments, other elemental data blocks may include packets.
From traffic processor 314, the data is provided to traffic converter 316. Traffic converter 316 receives the Rainer cells and retransmits them over the Utopia (Universal Test and Operating PHY Interface for ATM) bus (level 3) interface, which is a known industry standard, having a length of 64 bytes.
From traffic converter 316, the data is provided to SAR 318. SAR 318 provides ATM layer services, namely AAL5 segmentation and re-assembly (SAR). Additionally, SAR 318 provides ingress queuing and responds to backpressure from fabric 200 as part of the ingress queuing. SAR 318 provides one 256 K 64-byte shared memory packet buffer with per queue early packet discard (EPD) for congestion control. SAR 318 also converts cell formats from the format used by traffic processor 314 to another format for internal processing. SAR 318 internally converts the cell's format to another format having 48 bytes of data and 16 bytes of header information. The data is encapsulated in AAL5 format, for the embodiment; however, again, other formats may be used. SAR 318 provides regeneration of cells and a queuing point for cells received from CPE 102. It is also the initial discard point for cells for ingress transmission. SAR 318 also sets the definition for the cell, depending on the content of the header. The data can be transmitted in any one of AAL /0/1/3/4/5 format.
SAR 318 also provides the minimum gap shaping of cell traffic. Further detail on the shaper mechanism of the embodiment providing the minimum gap for the transmitted cells is provided later. Finally, SAR 318 generates traffic-regulated cells and releases them to traffic release module 320. The traffic release module 320 receives the Utopia-like data and transmits it to the core 200 over HSL 208.
Processor 322 in line card 300 provides housekeeping of all aspects of the I/O card selector 312, traffic processor 314, traffic converter 316, SAR 318 and traffic release modules 320.
The memory of buffer memory module 406 is logically organized to track 100 queues. The 100 queues comprise 32 sets of 3 queues which are each associated with a particular egress line card 204. Each set of queues for each egress line card 204 has three queues providing three levels of priority (high, medium, low). The contents of buffer memory module 406 include the data of the packet with revised header information for the ultimate destination line card. The memory is managed by pointer manager module 408 and controlled by buffer control module 407. As cells are removed from the FIFO in module 402 by cell re-assembly module 404, the packet is built up. Accordingly, SAR 318 must track when a series of transmitted cells constitutes a packet. After the packet is fully built, cell re-assembly module 404 notifies pointer manager 408 that the packet is ready to be sent. Pointer manager 408 manages memory relating to the data portions for the built packets. The pointer manager 408 utilizes linked lists to track the number of packets available to be sent. The cell re-assembly module 404 utilizes information in the cell header of the cell in traffic processor 314 to identify the queue in which the cell will be reassembled. Cell re-assembly module 404 provides the information to pointer manager 408 which uses the information to manage the reassembled packets in the buffer memory 406.
As soon as cell re-assembly module 404 notifies pointer manager 408 that the end of a packet has been received, pointer manager 408 updates the context related to the packet to be an enqueued packet which is stored in table memory 421. Pointer manager 408 then advises arbiter 416 that a packet is available to be sent for segmentation.
Segmentation module 412 utilizes information from pointer manager 408 to examine the location of the transmittable cells. It also uses information passed to it from the previously stored context by pointer manager 408 to determine how the data is to be processed. To create a transmittable cell, it generates AAL5 cells from the packets stored in buffer memory 406. Again, other cell formats could be generated. In the embodiment, up to one hundred packets may be simultaneously segmented, one per queue. Arbitrators 412 dictate the segmentation priority for segmentation module 418. For each queue, a segmentation context is created and saved. When a start of a frame buffer is read from memory the external header information is extracted therefrom and stored in its respective context. The header information is used to generate the internal header for each AAL5 internal cell destined for the switch fabric.
Forwarder 410 receives the cell information and stores the cell information in its own internal memory. This memory is separate from the buffer memory described earlier. It is noteworthy that forwarder 410 can have backpressure on each cell queue indirectly by backpressure affecting its arbiter in arbitration module 416. From the forwarder 410, the cell information is provided to notify shaper 414 that a cell is available. Forwarder 410 holds three cells in its internal memory.
Arbitration module 416 selects a queue from which a cell should be sent every cell time, if cells are available. Again, every cell time a cell is sent (if available) and after a number of cell times collectively a packet would be sent. The arbitration module 416 output then provides queue information to forwarder 410 to allow it to forward a cell to output module 418. The shaper 414 is a submodule of arbitration module 416. The shaper 414 performs the rate calculation for the high priority queues of the arbiter. The shaper also has a calculator, per queue, which feeds its own Work Conserving Round Robin (WCRR) scheduler which, in turn, feeds the exhaustive arbiter of arbitration module 416. The WCRR scheduler of the shaper receives priority over all other queue requests from forwarder 410. This priority provisioning ensures that the defined intercell gap of high priority queues in the embodiment is maintained.
Output module 418 converts the transmission rate of the cell from the internal 80 MHz to 111 MHz and forwards it to the core 200.
Further detail on the rate determining mechanism of shaper 414 is provided below. Referring to
The embodiment provides a minimum gap between cells by using down counter 502, CPU 322 and clock signal 510. This contrasts with a system which does not provide minimum gaps between cell transmissions, where once cells are available, they would be released to the system without any moderation to their timing.
Software operating on CPU 322 monitors bandwidth requirements of its associated CPEs to its line card 300. It will be understood that references CPU 322 include the software operating thereon. Accordingly, CPU 322 determines an optimum minimum gap which should be provided between transmission of cells. Further detail on the calculation of the optimum minimum gap is provided below. For circuit 500, CPU 322 determines a “desired cell rate” which is used to govern the release of cells to ensure that cells have a minimum gap between adjacent cells. The cell rate is based, in part, on the desired throughput bandwidth, the internal clock of shaper 414 and the size of the cell. As a cell is fixed in size, the minimum gap is always maintained, as long as the release of the cells is consistently synchronized, in some manner, to the cell rate. The desired bandwidth in provided by the user of switch 108. For each CPE connection , the user assigns a particular bandwidth limit. CPU 322 tracks and sums the aggregate bandwidth requirements for each egress line card 204. Shaper 414 will restrict all of the CPEs transmitting to a particular egress line card to the desired aggregate bandwidth limit. Each egress line card 204 will have an independent bandwidth limit.
The overall cell rate signal related to the cell rate is generated by down counter 502, CPU 322 and clock signal 510. CPU 322 provides a preset to down counter 502 via its data register which is a value which will enable down counter 502 to generate the cell rate signal at the required frequency. The decrementing of down counter 502 is controlled by pulses in clock signal 510, connected to the clock input of down counter 502. Once sufficient pulses have been provided to down counter 502 to bring its internal count to zero, down counter 502 generates a high logic signal on its zero-output terminal. The output value of the output terminal is also fed to the load enable input of down counter 502. Accordingly, as soon as down counter 502 counts to zero, the preset value from CPU 322 is loaded into down counter 502. Thereafter, on the next clock pulse from clock signal 510, the internal count of down counter 502 is no longer zero and the signal on the zero-output terminal goes to a low logic level. Accordingly, a pulse is generated by down counter 502 which depends on the frequency of clock pulse 510 and the preset value provided by CPU 322. The pulse is the cell rate signal.
The cell rate pulse signal provides the timing mechanism ensuring that a minimum cell gap is provided for cells. However, the embodiment further utilizes the cell rate signal to produce a queue eligible signal to handle internal backpressure and simultaneous queue requests from other systems, while still maintaining a minimum cell gap between cells. To accomplish this, circuit 500 takes the cell rate signal and produces a queue eligible signal which has the same frequency characteristics of the cell rate signal, but selectively masks the pulses when a cell should not be released because backpressure or credits are present for cells that have not yet been enqueued in the forwarder.
To produce the queue eligible signal, up/down counter 504 is used. Up/down counter 504 is an asynchronous device which counts up and down by one depending on the presence of an activation signal on its increment and decrement input terminals. The non-zero output terminal produces a high logic signal when a non-zero count value is currently set in up/down counter 504. A clear input signal clears up/down counter 504; it is connected to a signal from pointer manager 408 which is ANDed with a signal from forwarder 410 at AND gate 514. The internal count value stored in up/down counter 502 indicates a credit of cells which have to be transmitted.
Every cell rate pulse signal increments up/down counter 504 and, in most cases, the output signal goes to a high logic level. The output signal is ANDed with a backpressure signal decoded from backpressure decoder 420 by AND gate 506. If there is no backpressure, a high logic signal is provided to its input on logic AND gate 506 and accordingly, AND gate 506 generates a high logic level output, which indicates that a cell is releasable. The signal is provided to WCRR shaper 508 to arbitrate amongst its managed queues. When WCRR 508 services the release of the cell, it sends notification of the release of the cell to the decrement input terminal of up/down counter 504. Accordingly, the internal count decreases by one, indicating that the previously released cell has now been transmitted. In the event of a backpressure signal, AND gate 506 causes the queue eligible signal to indicate that a cell cannot be released, i.e., the logic high level is suppressed. The logic value of AND gate 506 is held in register 516.
Meanwhile, every cell rate pulse signal increments the internal count in up/down counter 504. Accordingly, it is possible that the internal count is tracking the availability of cells which may not exist. For example, no cells may be in the queue, or the packet relating to the cells has been fully sent, and accordingly, no more cells are associated with it. In the latter case, pointer manager 408 and forwarder 410 indicate this state and in such circumstances produces a signal to cause up/down counter 504 to be cleared through AND gate 512. In the former case, the pointer manager 408 will still indicate that a portion of the packet remains to be transmitted; however, the forwarder 410 will not indicate this state. Therefore the credits are maintained and new credits can be added. The output signal from counter 504 is ANDed with the cell available signal from forwarder 410 by AND gate 507. If a cell is available, a high logic signal is provided to an input of AND gate 507, which causes AND gate 507 to generate a high logic level output at node 516, indicating that a cell is releasable. In the event that no cells is available in forwarder 410, forwarder 410 generates a low logic signal for the cell available signal. The low logic signal causes AND gate 507 to provide a queue eligible signal indicating that a cell cannot be released, i.e. the high level logic is suppressed.
CPU 322 ultimately sets the frequency of the cell rate pulse signal. CPU 322 knows the rate for each new connection. Accordingly, the user assigns a bandwidth to each connection, to ensure that for a particular connection, the transmission rate in bits per second is limited to a maximum value, which translates into a minimum gap between cells. CPU 322 translates the assigned bandwidth, aggregates it with the bandwidths of other connections, and programs an appropriate value into counter 502.
Assuming that the count value loaded by CPU 322 is 2, for down counter 502, on each clock pulse, down counter decrements from 2 down to zero. On the zero count value, counter 502 generates a cell counter pulse 602. Assuming that backpressure decoder 420 (
In the embodiment, traffic is queued based on the egress line card 204. There are sets of queues for each egress line card 204. Multiple CPEs 102 may direct traffic to the same egress line card 204. The shaper 508 is used to shape all traffic directed towards a particular egress card 204. Accordingly, the cumulative output data stream 606 for the egress line cards may be like output stream 618, where traffic to egress line cards 204A, 204B and 204C are is being shaped by the embodiment. In circuit 200, for egress line card 204A, the count value in counter 502 is set to enable a cell to potentially be available for transmission to egress line card 204A every 2 cell times. Similarly for egress line card 204B, another circuit 200 has its counter 502 set to enable a cell to be potentially be available for transmission to egress line card 204B every 4 cell times. If a cell is available for transmission for both egress line cards 204A and 204B at the same time, the embodiment uses a round-robin scheme to select the card that will be serviced. It will be appreciated that traffic provided to an egress card 204 may include traffic from CPEs 102A, 102B and 102C. Each egress line card 204 will receive its own intercell gap for its own traffic (as the ingress card generates the gap) and when the cumulative traffic is combined, during the presence of an intercell gap for one stream of traffic for a given egress line card 204, traffic from another egress card 204 is inserted therein. For the illustrated example in data stream 618, egress card 204A has a minimum intercell gap of one cell per gap 614A and egress line card 204B has a minimum gap of three cells per gap 614B.
It is notable that in a packet-based system, a different mechanism would have to be used to ensure that the minimum gap is respected. The varying size of packets would need to be considered when providing the preset values for counter 502.
Processor 322 has access to information on the status of existing connections, the appearance of new connections, and the requested rates for each connection. Processor 322 sums the bandwidth requested per destination queue and determines a transmission rate for each queue utilizing the known maximum egress transmission rate. The sum of the transmission rates for all the queues should be lower or equal to the known maximum transmission rate, in order to reduce the possibility of backpressure signalling. The processor 322 apportions the available bandwidth (determined by the maximum transmission rate) to a desired bandwidth value for each ingress line card queue. Additional factors related to the transmission rate at each queue include the size of the data in bytes in a cell, the internal processing clock of the shaper 415 and the overall transmission rate. Accordingly, to establish a preset value for a given down counter 502, CPU 322 may utilize the following formula:
The subtraction of 1 is an offset value for down counter 502 to trigger the signal on a zero value.
From the above description, it will be seen that the embodiment describes a system providing a minimum gap between cells. The embodiment provides a simple circuit which may be implemented in FPGA.
It is noted that those skilled in the art will appreciate that various modification of detail may be made to the present embodiment, all of which would come within the scope of the invention.
|Cited Patent||Filing date||Publication date||Applicant||Title|
|US5353285 *||Dec 1, 1992||Oct 4, 1994||Alcatel N.V.||Time slot management system|
|US5570361 *||Jul 6, 1994||Oct 29, 1996||Fujitsu Limited||Apparatus and a method for supervising and controlling ATM traffic|
|US5777984 *||Apr 1, 1996||Jul 7, 1998||Motorola Inc.||Method and apparatus for controlling cell transmission rate in a cell based network in the presence of congestion|
|US5787072 *||Mar 15, 1996||Jul 28, 1998||Kabushiki Kaisha Toshiba||Flow control apparatus and flow control method|
|US5790521 *||Mar 27, 1996||Aug 4, 1998||The University Of Iowa Research Foundation||Marking mechanism for controlling consecutive packet loss in ATM networks|
|US5790545 *||Mar 14, 1996||Aug 4, 1998||Motorola Inc.||Efficient output-request packet switch and method|
|US5862127 *||Dec 12, 1996||Jan 19, 1999||Electronics And Telecommunications Research Institute||Method of controlling the peak cell rate spacing of multiplexed ATM traffic|
|US6052376 *||Dec 30, 1996||Apr 18, 2000||Hyundai Electronics America||Distributed buffering system for ATM switches|
|US6201792 *||May 14, 1998||Mar 13, 2001||3Com Corporation||Backpressure responsive multicast queue|
|US6215768 *||May 19, 1998||Apr 10, 2001||Hyundai Electronics Industries Co. Ltd.||High speed connection admission controller based on traffic monitoring and a method thereof|
|US6226306 *||Jun 13, 1997||May 1, 2001||Oki Electric Industry Co., Ltd.||Data transmission rate control using a transmission control scheme suitable for subbands forming an entire band|
|US6407983 *||Feb 20, 1998||Jun 18, 2002||Adc Telecommunications, Inc.||Circuit and method for shaping traffic in a virtual connection network|
|US6504824 *||Jan 22, 1999||Jan 7, 2003||Fujitsu Limited||Apparatus and method for managing rate band|
|US6791943 *||Feb 27, 1998||Sep 14, 2004||Agilent Technologies, Inc.||Event-based technique for determining instantaneous cell bandwidth in a digital communications network|
|US6888824 *||Oct 20, 2000||May 3, 2005||Cisco Technology, Inc.||Random early detection (RED) algorithm using marked segments to detect congestion in a computer network|
|US6975638 *||Oct 13, 2000||Dec 13, 2005||Force10 Networks, Inc.||Interleaved weighted fair queuing mechanism and system|
|US20020194321 *||Oct 15, 2001||Dec 19, 2002||Fujitsu Networks||End-to-end governed data transfers in a network|
|Citing Patent||Filing date||Publication date||Applicant||Title|
|US20150256468 *||Jan 29, 2015||Sep 10, 2015||Fujitsu Limited||Control method, information processing system, and information processing apparatus|
|U.S. Classification||370/231, 370/415|
|International Classification||H04L12/873, H04L12/26|
|Cooperative Classification||H04L2012/5679, H04L47/263, H04L49/506, H04L47/30, H04L2012/5681, H04L2012/5674, H04L12/5601, H04L2012/5635|
|European Classification||H04L47/26A, H04L47/30, H04L49/50C2, H04L12/56A|
|Jul 14, 2002||AS||Assignment|
Owner name: ALCATEL CANADA INC., CANADA
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:THIBODEAU, MARK JASON;GALWAY, JOHN WILLIAM;STERNE, JASON;AND OTHERS;REEL/FRAME:013106/0752;SIGNING DATES FROM 20020627 TO 20020702
|Mar 5, 2009||AS||Assignment|
Owner name: ALCATEL-LUCENT CANADA INC., CANADA
Free format text: MERGER;ASSIGNOR:ALCATEL CANADA INC.;REEL/FRAME:022351/0213
Effective date: 20070101
|Sep 28, 2012||FPAY||Fee payment|
Year of fee payment: 4
|Jan 30, 2013||AS||Assignment|
Owner name: CREDIT SUISSE AG, NEW YORK
Free format text: SECURITY INTEREST;ASSIGNOR:ALCATEL-LUCENT CANADA INC.;REEL/FRAME:029826/0927
Effective date: 20130130
|Sep 4, 2014||AS||Assignment|
Owner name: ALCATEL-LUCENT CANADA INC., CANADA
Free format text: RELEASE OF SECURITY INTEREST;ASSIGNOR:CREDIT SUISSE AG;REEL/FRAME:033686/0798
Effective date: 20140819
|Oct 18, 2016||FPAY||Fee payment|
Year of fee payment: 8